modelcontextprotocol/servers

4.4

Adjusted Score

4.4

Raw Score

100%

Time Factor

2026-07-10

Last Push

88.4K

Stars

TypeScript

Language

23.1K

Lines of Code

122

Files

Pattern Hits

2026-07-14

Scan Date

0.01

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 1MEDIUM 5LOW 70

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 76 distinct pattern matches across 10 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers50 hits · 50 pts

Severity	File	Line	Snippet	Context
LOW	src/memory/index.ts	547	export function registerKnowledgeGraphResource(	CODE
LOW	src/memory/index.ts	576	export function registerKnowledgeGraphSubscriptions(server: McpServer) {	CODE
LOW	src/everything/tools/simulate-research-query.ts	325	function getInterpretationsForTopic(	CODE
LOW	src/everything/__tests__/tools.test.ts	1059	function createMockServerWithTasks() {	CODE
LOW	src/filesystem/path-validation.ts	11	export function isPathWithinAllowedDirectories(absolutePath: string, allowedDirectories: string[]): boolean {	CODE
LOW	src/filesystem/lib.ts	76	function resolveRelativePathAgainstAllowedDirectories(relativePath: string): string {	CODE
LOW	src/filesystem/lib.ts	374	export async function searchFilesWithValidation(	CODE
LOW	src/filesystem/index.ts	724	async function updateAllowedDirectoriesFromRoots(requestedRoots: Root[]) {	CODE
LOW	src/time/test/time_server_test.py	85	def test_get_current_time_with_invalid_timezone():	CODE
LOW⚡	src/time/test/time_server_test.py	465	def test_get_local_tz_with_override():	CODE
LOW⚡	src/time/test/time_server_test.py	472	def test_get_local_tz_with_invalid_override():	CODE
LOW⚡	src/time/test/time_server_test.py	479	def test_get_local_tz_with_valid_iana_name(mock_get_localzone):	CODE
LOW⚡	src/time/test/time_server_test.py	488	def test_get_local_tz_when_none_returned(mock_get_localzone):	CODE
LOW⚡	src/time/test/time_server_test.py	496	def test_get_local_tz_handles_windows_timezones(mock_get_localzone):	CODE
LOW	src/time/test/time_server_test.py	523	def test_get_local_tz_various_timezones(mock_get_localzone, timezone_name):	CODE
LOW	src/fetch/tests/test_server.py	29	def test_url_with_query_params(self):	CODE
LOW	src/fetch/tests/test_server.py	84	def test_empty_content_returns_error(self):	STRING
LOW	src/fetch/tests/test_server.py	149	async def test_allows_when_robots_txt_allows_all(self):	CODE
LOW	src/fetch/tests/test_server.py	168	async def test_blocks_when_robots_txt_disallows_all(self):	CODE
LOW	src/fetch/tests/test_server.py	247	async def test_fetch_json_returns_raw(self):	CODE
LOW	src/fetch/src/mcp_server_fetch/server.py	27	def extract_content_from_html(html: str) -> str:	CODE
LOW	src/fetch/src/mcp_server_fetch/server.py	66	async def check_may_autonomously_fetch_url(url: str, user_agent: str, proxy_url: str \| None = None) -> None:	CODE
LOW⚡	src/git/tests/test_server.py	283	def test_validate_repo_path_no_restriction():	CODE
LOW⚡	src/git/tests/test_server.py	288	def test_validate_repo_path_exact_match(tmp_path: Path):	CODE
LOW⚡	src/git/tests/test_server.py	295	def test_validate_repo_path_subdirectory(tmp_path: Path):	CODE
LOW⚡	src/git/tests/test_server.py	304	def test_validate_repo_path_outside_allowed(tmp_path: Path):	CODE
LOW⚡	src/git/tests/test_server.py	328	def test_validate_repo_path_symlink_escape(tmp_path: Path):	CODE
LOW⚡	src/git/tests/test_server.py	344	def test_git_diff_rejects_flag_injection(test_repository):	CODE
LOW⚡	src/git/tests/test_server.py	480	def test_git_create_branch_rejects_flag_injection(test_repository):	CODE
LOW⚡	src/git/tests/test_server.py	489	def test_git_create_branch_rejects_base_branch_flag_injection(test_repository):	CODE
LOW⚡	src/git/tests/test_server.py	495	def test_git_log_rejects_timestamp_flag_injection(test_repository):	CODE
LOW⚡	src/git/tests/test_server.py	504	def test_git_branch_rejects_contains_flag_injection(test_repository):	CODE
LOW	src/git/tests/test_server.py	35	def test_git_checkout_existing_branch(test_repository):	CODE
LOW	src/git/tests/test_server.py	42	def test_git_checkout_nonexistent_branch(test_repository):	CODE
LOW	src/git/tests/test_server.py	75	def test_git_branch_not_contains(test_repository):	CODE
LOW	src/git/tests/test_server.py	99	def test_git_add_specific_files(test_repository):	CODE
LOW	src/git/tests/test_server.py	112	def test_git_add_rejects_path_traversal(test_repository):	CODE
LOW	src/git/tests/test_server.py	127	def test_git_add_rejects_absolute_path_outside(test_repository):	CODE
LOW	src/git/tests/test_server.py	153	def test_git_diff_unstaged_empty(test_repository):	CODE
LOW	src/git/tests/test_server.py	168	def test_git_diff_staged_empty(test_repository):	CODE
LOW	src/git/tests/test_server.py	245	def test_git_create_branch_from_base(test_repository):	CODE
LOW	src/git/tests/test_server.py	271	def test_git_show_initial_commit(test_repository):	CODE
LOW	src/git/tests/test_server.py	316	def test_validate_repo_path_traversal_attempt(tmp_path: Path):	CODE
LOW	src/git/tests/test_server.py	356	def test_git_checkout_rejects_flag_injection(test_repository):	CODE
LOW	src/git/tests/test_server.py	368	def test_git_diff_allows_valid_refs(test_repository):	CODE
LOW	src/git/tests/test_server.py	394	def test_git_checkout_allows_valid_branches(test_repository):	CODE
LOW	src/git/tests/test_server.py	412	def test_git_diff_rejects_malicious_refs(test_repository):	CODE
LOW	src/git/tests/test_server.py	438	def test_git_checkout_rejects_malicious_refs(test_repository):	CODE
LOW	src/git/tests/test_server.py	458	def test_git_show_rejects_flag_injection(test_repository):	CODE
LOW	src/git/tests/test_server.py	467	def test_git_show_rejects_malicious_refs(test_repository):	CODE

Self-Referential Comments5 hits · 16 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	src/git/tests/test_server.py	335	# Create a symlink inside allowed that points outside	COMMENT
MEDIUM	src/git/tests/test_server.py	64	# Create a new branch and commit to it	COMMENT
MEDIUM	src/git/tests/test_server.py	78	# Create a new branch and commit to it	COMMENT
MEDIUM	src/git/tests/test_server.py	373	# Create a branch with a commit for diffing	COMMENT
MEDIUM	src/git/tests/test_server.py	399	# Create a branch to checkout	COMMENT

Fake / Example Data7 hits · 8 pts

Severity	File	Line	Snippet	Context
LOW⚡	src/memory/__tests__/knowledge-graph.test.ts	272	{ name: 'Acme Corp', entityType: 'company', observations: ['tech company'] },	CODE
LOW⚡	src/memory/__tests__/knowledge-graph.test.ts	276	{ from: 'Alice', to: 'Acme Corp', relationType: 'works_at' },	CODE
LOW⚡	src/memory/__tests__/knowledge-graph.test.ts	277	{ from: 'Bob', to: 'Acme Corp', relationType: 'competitor' },	CODE
LOW	src/memory/__tests__/knowledge-graph.test.ts	290	expect(result.entities[0].name).toBe('Acme Corp');	CODE
LOW	src/memory/__tests__/knowledge-graph.test.ts	318	expect(result.relations[0].to).toBe('Acme Corp');	CODE
LOW	src/everything/__tests__/tools.test.ts	640	name: 'John Doe',	CODE
LOW	src/everything/__tests__/tools.test.ts	662	expect(result.content[1].text).toContain('John Doe');	CODE

Verbosity Indicators4 hits · 8 pts

Severity	File	Line	Snippet	Context
LOW	src/filesystem/path-validation.ts	71	// On Windows, we need to check if both paths are on the same drive	COMMENT
LOW⚡	src/filesystem/__tests__/path-validation.test.ts	949	// Step 1: validatePath would pass for legitimate file	COMMENT
LOW⚡	src/filesystem/__tests__/path-validation.test.ts	952	// Step 2: Race condition - replace file with symlink after validation	COMMENT
LOW⚡	src/filesystem/__tests__/path-validation.test.ts	956	// Step 3: Read operation follows symlink to forbidden location	COMMENT

Structural Annotation Overuse3 hits · 7 pts

Severity	File	Line	Snippet	Context
LOW⚡	src/filesystem/__tests__/path-validation.test.ts	949	// Step 1: validatePath would pass for legitimate file	COMMENT
LOW⚡	src/filesystem/__tests__/path-validation.test.ts	952	// Step 2: Race condition - replace file with symlink after validation	COMMENT
LOW⚡	src/filesystem/__tests__/path-validation.test.ts	956	// Step 3: Read operation follows symlink to forbidden location	COMMENT

Magic Placeholder Names1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	README.md	123	"GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"	CODE

Over-Commented Block2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	src/everything/tools/trigger-url-elicitation.ts	121	// Key the one-shot error-path marker on inputs the client resends	COMMENT
LOW	src/everything/tools/trigger-url-elicitation.ts	141	// 1. The prerequisite points at a different URL than the one that	COMMENT

Excessive Try-Catch Wrapping2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	src/time/src/mcp_server_time/server.py	56	except Exception as e:	CODE
LOW	src/time/src/mcp_server_time/server.py	215	except Exception as e:	CODE

Redundant / Tautological Comments1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	src/git/src/mcp_server_git/server.py	264	# Check if repo_path is the same as or a subdirectory of allowed_repository	COMMENT

Modern Structural Boilerplate1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	scripts/release.py	59	def update_version(self, version: Version) -> None: ...	CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings